mirror of
https://github.com/nomadkaraoke/karaoke-gen.git
synced 2026-11-20 13:07:57 +09:00
## Summary The review button now appears only once a job is fully prepared: stems separated, auto-approval re-scored with them, AI lyric corrections generated and applied on the server, and review audio + waveforms cached. The browser no longer applies AI corrections by itself, so there is one code path. Prompted by job ae995697 (a Made For You order): the review button showed at 18:29, but the stems, backing verdict and vocal waveform only existed from 18:32, and the server pre-apply had aborted on a duplicate-word check, leaving the browser to apply corrections on load. ## Changes - **Hold every job until stems land** (`review_gate.route_after_scoring`). Before, only jobs whose lyrics would auto-ship were held, so Made For You and lyrics-gated jobs opened review early. Same kill switch (`AUTO_APPROVAL_AUDIO_HOLD_ENABLED`) and 20-minute backstop. - **Generate AI suggestions on the API service before parking.** The hold is released inside the audio-separation job, which has no LLM credentials, so that job only applies an existing cache. - **`enter_human_review` prepares everything before AWAITING_REVIEW**: pre-apply (generating on a cache miss), then `review_assets.prepare_review_assets` (OGG transcodes, backing waveform, vocal peak envelope), then the transition. - **Non-strict pre-apply for human review** (`build_applied_segments(strict=False)`): what "Accept All" produces. Stale/duplicate signals are recorded as `warnings`. The auto-ship path stays strict. - **Removed the browser's on-load auto-run/auto-apply** from `useAutoCorrect`. - **Job card shows "[5/10] Preparing review"** while held (new summary field + 33 locales). - Docs: ARCHITECTURE review-gate step, `docs/archive/2026-11-19-review-ready-gate.md`. Trade-off: Made For You and lyrics-gated jobs reach review (and send the review-ready notification) ~3 minutes later. ## Testing - Backend unit suite: 7294 passed. Locally failing: 8 emulator-integration tests (something unrelated listens on :8080 so they don't skip; CI runs them against real emulators) and 1 locale test that tripped on a gitignored translation snapshot (passes once removed). - New/updated tests: review gate (review-verdict jobs held, kill switch, prepare-before-transition order, suggestions generated before parking, no double wait, missing job), non-strict apply, duplicate-word pre-apply (ae995697 case), review_assets. - Frontend Jest: 1834 passed; no type errors in touched files. - Local CodeRabbit: 2 minor findings fixed, re-review clean. @coderabbitai ignore 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_012RYLVVdAxGitbw1FhYP4e4 --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
207 lines
7.0 KiB
TOML
207 lines
7.0 KiB
TOML
[tool.poetry]
|
|
name = "karaoke-gen"
|
|
version = "0.298.0"
|
|
description = "Generate karaoke videos with synchronized lyrics. Handles the entire process from downloading audio and lyrics to creating the final video with title screens."
|
|
authors = ["Andrew Beveridge <andrew@beveridge.uk>"]
|
|
license = "MIT"
|
|
readme = "README.md"
|
|
packages = [
|
|
{ include = "karaoke_gen" },
|
|
{ include = "backend" }
|
|
]
|
|
include = [
|
|
# The Next.js static export is generated at build time and gitignored (see #876).
|
|
# Poetry's plain-string include respects .gitignore and would DROP a gitignored
|
|
# path from the wheel; the dict form with an explicit `format` overrides .gitignore
|
|
# so the built frontend is still bundled (needed for the CLI local-review UI).
|
|
# Wheel-only: the sdist would balloon past PyPI's 10 GB cap, so bundle in the wheel only.
|
|
{ path = "karaoke_gen/nextjs_frontend/out/**/*", format = ["wheel"] },
|
|
"karaoke_gen/lyrics_transcriber/output/fonts/*",
|
|
"karaoke_gen/lyrics_transcriber/output/cdgmaker/images/*",
|
|
"karaoke_gen/lyrics_transcriber/output/cdgmaker/transitions/*",
|
|
# Skip/include lists for the YouTube description backfill worker (must ship in
|
|
# the Cloud Run image so the scheduled worker can read them).
|
|
"backend/data/youtube_backfill/*.txt"
|
|
]
|
|
homepage = "https://github.com/nomadkaraoke/karaoke-gen"
|
|
repository = "https://github.com/nomadkaraoke/karaoke-gen"
|
|
documentation = "https://github.com/nomadkaraoke/karaoke-gen/blob/main/README.md"
|
|
|
|
[tool.poetry.dependencies]
|
|
python = ">=3.10,<3.14"
|
|
torch = ">=2.7"
|
|
requests = ">=2"
|
|
beautifulsoup4 = ">=4"
|
|
flacfetch = ">=0.9.0"
|
|
lyricsgenius = ">=3"
|
|
fetch-lyrics-from-genius = ">=0.1"
|
|
pillow = ">=10.1"
|
|
pyinstaller = ">=6.3"
|
|
google-api-python-client = "2.193.0"
|
|
google-auth = "2.49.1"
|
|
google-auth-oauthlib = "1.3.0"
|
|
google-auth-httplib2 = "0.3.0"
|
|
thefuzz = ">=0.22"
|
|
numpy = ">=2"
|
|
audio-separator = { version = ">=0.43.0", extras = ["cpu"] }
|
|
lyrics-converter = ">=0.2.1"
|
|
# lyrics_transcriber is now a subpackage of karaoke_gen (karaoke_gen/lyrics_transcriber/)
|
|
# Dependencies from vendored lyrics_transcriber:
|
|
mutagen = ">=1.47" # For LRCLIB provider to get track duration for better matching
|
|
python-slugify = ">=8"
|
|
syrics = ">=0"
|
|
karaoke-lyrics-processor = ">=0.6"
|
|
dropbox = ">=12"
|
|
spacy = ">=3.8.7"
|
|
srsly = ">=2.5.1"
|
|
tqdm = ">=4.67"
|
|
python-levenshtein = ">=0.26"
|
|
transformers = ">=4.47"
|
|
metaphone = ">=0.6"
|
|
nltk = ">=3.9"
|
|
spacy-syllables = ">=3"
|
|
syllables = ">=1"
|
|
fonttools = ">=4.55"
|
|
ollama = ">=0.4.7"
|
|
shortuuid = ">=1.0.13"
|
|
nest-asyncio = ">=1.5"
|
|
openai = ">=1.63.2"
|
|
langgraph = ">=0.2.0"
|
|
langchain = ">=0.3.0"
|
|
langchain-core = ">=0.3.0"
|
|
langchain-openai = ">=0.2.0"
|
|
langchain-anthropic = ">=0.2.0"
|
|
anthropic = ">=0.109.0" # direct dep: auto-correct structured outputs (output_config)
|
|
langchain-ollama = ">=0.2.0"
|
|
langchain-google-genai = ">=2.0.0"
|
|
langfuse = ">=3.0.0"
|
|
jiwer = ">=3.0.0"
|
|
kbputils = "^0.0.16"
|
|
attrs = ">=24.2.0"
|
|
cattrs = ">=24.1.2"
|
|
toml = ">=0.10"
|
|
argparse = ">=1.4.0"
|
|
psutil = "^7.0.0"
|
|
pyperclip = "*"
|
|
pytest-asyncio = "*"
|
|
ffmpeg-python = "^0.2.0"
|
|
python-multipart = "^0.0.20"
|
|
python-docx = ">=1.1.0"
|
|
yt-dlp = ">=2024.0.0"
|
|
matplotlib = ">=3"
|
|
# Backend API dependencies
|
|
fastapi = ">=0.104.0"
|
|
uvicorn = { version = ">=0.24.0", extras = ["standard"] }
|
|
pydantic = ">=2.5.0"
|
|
pydantic-settings = ">=2.1.0"
|
|
httpx = ">=0.25.0"
|
|
tenacity = "^8.2.0" # Retry logic for external service calls
|
|
google-cloud-firestore = "2.26.0"
|
|
google-cloud-compute = "^1.0.0"
|
|
# AWS encoding worker control (EC2 start/stop/describe) — backend/services/aws_encoding_compute.py
|
|
boto3 = "^1.34"
|
|
google-cloud-storage = "3.10.1"
|
|
google-cloud-secret-manager = "2.26.0"
|
|
google-cloud-monitoring = "2.29.1" # Cloud Monitoring for YouTube API quota metrics
|
|
google-cloud-tasks = "2.21.0" # Cloud Tasks for worker coordination (Phase 1 scalability)
|
|
google-cloud-run = "0.15.0" # Cloud Run Jobs for long-running video encoding (Phase 2 scalability)
|
|
google-cloud-logging = ">=3.9.0" # Cloud Logging for error monitoring
|
|
python-dotenv = ">=1.0.0"
|
|
pydub = ">=0.25.1"
|
|
# Google / Apple ID-token verification (JWKS) for mobile sign-in
|
|
pyjwt = { version = ">=2.8.0", extras = ["crypto"] }
|
|
# Payment and email services
|
|
stripe = "^14.1.0"
|
|
email-validator = ">=2.0.0" # For Pydantic EmailStr validation
|
|
# Web Push notifications
|
|
pywebpush = ">=2.0.0"
|
|
# OpenTelemetry for distributed tracing
|
|
opentelemetry-api = ">=1.20.0"
|
|
opentelemetry-sdk = ">=1.20.0"
|
|
opentelemetry-instrumentation-fastapi = ">=0.41b0"
|
|
opentelemetry-instrumentation-httpx = ">=0.41b0"
|
|
opentelemetry-instrumentation-logging = ">=0.41b0"
|
|
opentelemetry-exporter-gcp-trace = ">=1.6.0"
|
|
opentelemetry-resourcedetector-gcp = ">=1.6.0a0"
|
|
# Optional: Local Whisper transcription (install with: pip install karaoke-gen[local-whisper])
|
|
whisper-timestamped = { version = ">=1.15.0", optional = true }
|
|
aiohttp = "^3.13.2"
|
|
|
|
[tool.poetry.group.dev.dependencies]
|
|
black = ">=23"
|
|
poetry = "*"
|
|
pytest = ">=7.0"
|
|
pytest-cov = ">=4.0"
|
|
pytest-mock = ">=3.10"
|
|
pytest-asyncio = "*"
|
|
|
|
# Make dev dependencies available as optional extras for pip install
|
|
# These need to be declared as optional dependencies first
|
|
[tool.poetry.dependencies.black]
|
|
version = ">=23"
|
|
optional = true
|
|
|
|
[tool.poetry.dependencies.pytest]
|
|
version = ">=7.0"
|
|
optional = true
|
|
|
|
[tool.poetry.dependencies.pytest-cov]
|
|
version = ">=4.0"
|
|
optional = true
|
|
|
|
[tool.poetry.dependencies.pytest-mock]
|
|
version = ">=3.10"
|
|
optional = true
|
|
|
|
[tool.poetry.extras]
|
|
# Local Whisper transcription support - optional, heavy dependencies
|
|
# Install with: pip install karaoke-gen[local-whisper]
|
|
# For CPU-only installation (recommended for systems without GPU):
|
|
# pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu
|
|
# pip install karaoke-gen[local-whisper]
|
|
local-whisper = ["whisper-timestamped"]
|
|
|
|
# Development/testing dependencies (pytest-asyncio is already a main dependency)
|
|
# Install with: pip install -e ".[dev]" or pip install -e ".[local-whisper,dev]"
|
|
dev = ["black", "pytest", "pytest-cov", "pytest-mock"]
|
|
|
|
[tool.poetry.scripts]
|
|
karaoke-gen = 'karaoke_gen.utils.gen_cli:main'
|
|
karaoke-gen-remote = 'karaoke_gen.utils.remote_cli:main'
|
|
karaoke-bulk = 'karaoke_gen.utils.bulk_cli:main'
|
|
|
|
[tool.black]
|
|
line-length = 140
|
|
|
|
[build-system]
|
|
requires = ["poetry-core"]
|
|
build-backend = "poetry.core.masonry.api"
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests/unit", "tests/integration", "backend/tests"]
|
|
python_files = ["test_*.py"]
|
|
addopts = [
|
|
"--asyncio-mode=auto",
|
|
"-v",
|
|
"--tb=short",
|
|
]
|
|
markers = [
|
|
"slow: marks tests as slow (deselect with '-m \"not slow\"')",
|
|
"integration: marks tests as integration tests",
|
|
"asyncio: mark test as async",
|
|
"emulator: marks tests requiring GCP emulators",
|
|
]
|
|
filterwarnings = [
|
|
"ignore::DeprecationWarning",
|
|
"ignore:'audioop' is deprecated:DeprecationWarning",
|
|
"ignore::RuntimeWarning",
|
|
"ignore::UserWarning",
|
|
]
|
|
|
|
[tool.coverage.run]
|
|
# Exclude lyrics_transcriber subpackage from coverage since it was a separate vendored package
|
|
# with its own test suite - including it in karaoke_gen coverage would unfairly lower the percentage
|
|
omit = [
|
|
"karaoke_gen/lyrics_transcriber/*",
|
|
]
|